Segmentation of Mueller matrix images under non-uniform illumination

The recently proposed restoration-segmentation algorithms dedicated to polarization encoded images suffer two important limitations: the number of classes into which the image is segmented is not obtained automatically, and more importantly the quality of the segmentation is affected by the nonuniformity of the illumination of the scene. We propose here a new method addressing these issues. It is based on a global estimation-segmentation approach, explicitly modeling the nonuniform illumination. The physical admissibility of the retrieved Mueller matrices is ensured. Results stemming from synthetic and real data are provided and support the proposed approach.